Open-Box
OpenWrt 一体化透明代理方案:一条命令装完 sing-box 内核 + 管理面板,浏览器打开即用
HYSEN LABS DIRECTORY
Deployment tag · curated repositories and deep analysis.
OpenWrt 一体化透明代理方案:一条命令装完 sing-box 内核 + 管理面板,浏览器打开即用
AI-native workspace for local shells and remote machines.Zero Webview, zero OpenSSL, zero telemetry, and no app subscription.
WebHomeTV 基于FongMi二次开发,增强了 WebHome 自定义首页、App Native SDK、网盘链接检测 和 Nostr推荐首页。 这个项目的核心目标是让 CSP 站点首页可以变成一个真正可开发的网页应用:开发者可以用 HTML/CSS/JavaScript 定制首页,再通过 App 暴露的 Native 能力完成搜索、播放、跨域请求、资源代理、最近观看、网盘检测和状态同步。
Browser-native side panel for Hermes Agent — connect web context to your local Hermes runtime.
Local Android file converter built with Kotlin and Jetpack Compose. Convert files on device, with no ads, accounts, or upload-based fallback.
Voice-to-text with push-to-talk for Wayland compositors
Tiny Model, Big Logic: Diversity-Driven Optimization Elicits Large-Model Reasoning Ability in VibeThinker-1.5B
AI-powered daily intelligence for indie hackers and builders. 20 questions, 10+ sources, every morning.
Fun-ASR speech recognition models, with native Hugging Face Transformers support for Fun-ASR-Nano and separate FunASR, vLLM and llama.cpp deployment paths.
🎙️ AI Dictation App - Open Source and Local-first ⚡ Type 3x faster, no keyboard needed. 🆓 Powered by open source models, works offline, fast and accurate.
Open-source Reflect rewrite: A local-first AI agent-friendly Markdown note-taking app
Agent OS: keep specialist agents in a hub, spin up a temporary orchestrator per task. Local-first, works with any model.
Collection of offline first developer utilities available as non-electron desktop application. all in one place, cross-platform, 10MB app!
Row-Bot - Personal AI Sovereignty. A local-first AI assistant with integrated tools, a personal knowledge graph, voice, vision, shell, browser automation, scheduled tasks, health tracking, and messaging channels. Run locally via Ollama or add opt-in cloud models. Your data stays on your machine.
Plugin to integrate Learning to Rank (aka machine learning for better relevance) with Elasticsearch
指纹浏览器、纯协议全自动ChatGPT FREE注册机+Codex自动接码授权、对接提链服务器
NobodyWho is an inference engine that lets you run LLMs locally and efficiently on any device.
Own your compute, own your intelligence. Time to build your Personal AI Data Center.
Virtualized Elastic KV Cache for Dynamic GPU Sharing and Beyond
Open-source, local-first Granola/Otter alternative that Claude Code, Codex, Cursor, and any MCP client can query. Meetings, calls, and voice memos transcribed on-device into markdown you own.